Attempted the same with Deepseek-V4.1-Flash
So Mimo-2.6-pro vs Deepseek-v4.1-flash One-shot, direct api call, with high thinking. Total tokens needed 60k (in video there is a typo) Cost pretty much nothing, it's soo cheap. Few things are missing here, but overall as per
You’re paying for AI in the wrong places.
The costliest mistake in the AI business is forcing a powerful model to make every single decision. Filter. Evaluate. Select. Weed out. Route. You don’t always need the most expensive model for that. That’s why the Jev + DeepSeek +
I just told deepseek v4.1 flash to look up some random guy's youtube channel and design in freecad what he designed in his videos
I literally touched nothing, it did everything from end to end money spent : 0.1$ (not even joking) the guy's youtube channel :
This is real world GPT-6 Luna vs DeepSeek V4.1 Flash.
Look at NavBar UI design
You have reached the end of the archive
All of deepseek